harness
claude에이전트 팀 & 스킬 아키텍트 v2. 도메인/프로젝트에 맞는 하네스를 구성하고, 전문 에이전트를 정의하며, 에이전트가 사용할 스킬을 생성하는 메타 스킬. 워크플로우 오케스트레이션 · 퍼시스턴트 에이전트 협업 · 서브에이전트 위임 3중 실행 모드 지원.
2 skills
Open-source local-first token reduction plugin for Claude Code with BM25 + vector hybrid retrieval, reranking, AST chunking, and compressed context packets.
Plugin claude-token-reducer from marketplace Madhan230205-claude-token-reducer in Madhan230205/token-reducer. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
token-reducerUse this skill whenever the user needs to reduce context bloat, lower token usage, summarize large code/docs corpora, run FTS plus embeddings retrieval, rerank top chunks, and produce compact context packets before implementation work. Also trigger when users say context is too long, reduce tokens,
/claude-token-reducer:token-reducerBuild a compact context packet with preprocess, BM25-ranked FTS retrieval, adaptive vector fallback, reranked top-K chunks (default 3 from settings), relevance-floor filtering, and compression.
context-compressorCompresses top retrieval chunks into citation-rich summary packets that preserve intent while cutting token usage.
hybrid-retrieverRuns hybrid retrieval with strict FTS-first policy, BM25 lexical ranking, vector merge, and top 3-5 reranking for token-efficient context selection.
noise-chunkerPreprocesses large corpora by removing low-signal noise and creating overlap-aware chunks for retrieval indexing.
se-ops-delegateDelegates software engineering operations to focused subagents using compressed context packets to keep the main conversation lean.
context7runs: npx -y @upstash/context7-mcp
python ${CLAUDE_PLUGIN_ROOT}/hooks/userprompt_guard.py
에이전트 팀 & 스킬 아키텍트 v2. 도메인/프로젝트에 맞는 하네스를 구성하고, 전문 에이전트를 정의하며, 에이전트가 사용할 스킬을 생성하는 메타 스킬. 워크플로우 오케스트레이션 · 퍼시스턴트 에이전트 협업 · 서브에이전트 위임 3중 실행 모드 지원.
2 skills
v11.23.0 - UberLLM seats, isolated presets and accurate run results. 31 personas, 56 commands, 64 skills. Run /octo:setup.
71 skills · 56 commands · hooks
Per-stage model routing + pre-flight cost gate for Claude Code ultracode dynamic workflows. Pins an explicit model + effort on every agent() subagent stage, estimates cost before launch, and ships a static guard + PreToolUse gate that flag stages which would silently inherit the session's Opus model. Zero dependencies, no telemetry, MIT.
1 skill · 12 commands · hooks
Point it at a GitHub issue and get back a reviewed pull request. Hyperflow turns one AI coding session into a structured engineering pipeline: plan sharpens and decomposes the work, dispatch fans out parallel workers, and a domain specialist reviews every step — nothing ships unreviewed. 18 skills, 22 specialist reviewer and investigator agents, adaptive depth so a 5-line fix never triggers a deep run, and persistent per-project memory that lives in your repo and never leaves it. Runs on whatever model your session already uses — zero config, no API keys, no daemon. Works across Claude Code, Codex App/CLI, OpenCode, Grok, Antigravity, and Cursor.
18 skills · 23 agents · hooks
Edit CapCut and JianYing (剪映) projects from Claude Code — subtitles and SRT/ASS import, timing, speed, volume, keyframes, masks, filters and effects, templates, lint --fix, render previews, and cutting long-form to shorts.
1 skill · hooks
GoalBuddy: turn broad work into pressured /goal runs with oracles, local boards, receipts, and verification.
1 skill · 1 command · 3 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.